Benchmark cell Prediction Methods-5-011-2025-table

load libraries————————————

1. Load and Subset Normal CD4 T Cells

All_samples_Merged <- readRDS("../All_samples_Merged_Benchmarked_05-11-2025.rds")

Idents(All_samples_Merged) <- "orig.ident"
table(All_samples_Merged@active.ident)

      L1       L2       L3       L4       L5       L6       L7 CD4T_lab CD4T_10x 
    5825     5935     6428     6006     6022     5148     5331     5106     3504 

2. Create the annotation summary table

library(dplyr)
library(tidyr)
library(purrr)

methods <- c(
  "predicted.id",             #scPred
  "predicted.celltype.l2",    # Azimuth (l2 prediction)
  "singler.immune",           # Example of other annotation methods like SingleR
  "Prediction",               #STCAT
  "scATOMIC_annotation"      #scATOMIC
  )

annotation_summary <- map_dfr(methods, function(m) {
  df <- All_samples_Merged@meta.data
  df %>%
    group_by(orig.ident, label = .data[[m]]) %>%
    summarise(n = n(), .groups = "drop") %>%
    group_by(orig.ident) %>%
    slice_max(n, n = 1, with_ties = FALSE) %>%
    mutate(method = m)
})



# Set the order of methods
annotation_summary$method <- factor(annotation_summary$method, levels = methods)

head(annotation_summary)

# Should show columns: orig.ident | label | n | method

3. Convert to matrix format for plotting

library(tidyr)
library(ggplot2)

annotation_matrix <- annotation_summary %>%
  select(method, orig.ident, label) %>%
  pivot_wider(names_from = orig.ident, values_from = label)

# Rename methods for the plot
annotation_summary <- annotation_summary %>%
  mutate(method = recode(method,
                         "predicted.id" = "scPred",
                         "predicted.celltype.l2" = "Azimuth.l2",
                         "singler.immune" = "SingleR(Immune)",
                         "Prediction" = "STCAT",
                         "scATOMIC_annotation" = "scATOMIC"))

# Save the annotation summary table to a CSV file for further analysis

write.csv(annotation_summary, "annotation_summary_table.csv", row.names = FALSE)